© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15523
    Prev
    Next
    INDEX
    Explanations

    rounding, Federated Learning, limit, OCO, recall

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron lights up on content-bearing tokens (i.e. non‐function words such as nouns, verbs, and adjectives), ignoring common stopwords.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    на
    0.81
    마
    0.75
    એ
    0.71
     Pension
    0.71
    서
    0.67
     Flats
    0.64
     नए
    0.63
     Rays
    0.62
     الى
    0.62
    要想
    0.62
    POSITIVE LOGITS
     иссле
    0.95
    েও
    0.90
    ετε
    0.90
     именем
    0.80
    淯
    0.80
     estadounid
    0.79
     tubig
    0.79
    게요
    0.78
     proté
    0.77
     idempotent
    0.77
    Activations Density 0.000%

    No Known Activations